{ "openapi": "3.0.1", "info": { "title": "Speech to Text with Timestamps (SRT/VTT) – Chinese & Japanese", "description": "Transcribe audio and video files to SRT/VTT subtitles and text with timestamps. Accurate on Chinese (Simplified or Traditional output) and Japanese, works for many other languages. Pay only for minutes transcribed; files that fail to download or decode are free. Built for AI agents.", "version": "0.0", "x-build-id": "0ozZyyX0bUK7CPXn3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kumo-data-tools~speech-to-text-srt/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kumo-data-tools-speech-to-text-srt", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kumo-data-tools~speech-to-text-srt/runs": { "post": { "operationId": "runs-sync-kumo-data-tools-speech-to-text-srt", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kumo-data-tools~speech-to-text-srt/run-sync": { "post": { "operationId": "run-sync-kumo-data-tools-speech-to-text-srt", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "audioUrls": { "title": "Audio or video file URLs", "maxItems": 50, "type": "array", "description": "Direct download links to audio or video files you have the right to transcribe (mp3, m4a, wav, ogg, opus, flac, mp4, mov, webm, ...). Up to 50 files per run, 500 MB and 60 minutes each. Leave empty to transcribe a short bundled sample for free.", "items": { "type": "string" } }, "language": { "title": "Spoken language", "type": "string", "description": "Language code of the speech, e.g. zh, zh-cn, zh-tw, ja, en, ko. Leave empty to auto-detect. Setting it improves accuracy.", "default": "" }, "chineseScript": { "title": "Chinese characters", "enum": [ "auto", "simplified", "traditional", "keep" ], "type": "string", "description": "For Chinese speech only (segments detected as Japanese are left unchanged). auto = Traditional for zh-tw, Simplified otherwise.", "default": "auto" }, "outputFormats": { "title": "Output files", "maxItems": 4, "uniqueItems": true, "type": "array", "description": "Files written to the run's key-value store for each input (links are in the dataset). The dataset always contains the segments with timestamps.", "items": { "type": "string", "enum": [ "srt", "vtt", "txt", "json" ], "enumTitles": [ "SRT subtitles", "WebVTT subtitles", "Plain text", "JSON segments" ] }, "default": [ "srt", "vtt", "txt" ] }, "maxSegmentSeconds": { "title": "Max subtitle segment length (seconds)", "minimum": 5, "maximum": 30, "type": "integer", "description": "Speech is split at pauses; segments stay about this long or shorter. 5-30.", "default": 15 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }